Search

Technically, residential energy management systems are fundamental sectors in the smart grids for implementing demand response programs in the layer of households for managing energy consumption and reducing energy bills. The paper proposes a novel energy management scheme that takes production and usage into account based on a heuristic searching operation. In addition to modelling the grid, renewable energy sources, batteries, and electric vehicles, various kinds of electrical and thermal devices have been examined, including air conditioners, water heaters, vacuum cleaners etc. A method is developed for solving the objective constraint issue in a smart home in order to reduce energy consumption and determine feasible operation states among the various loads. Moreover, this paper proposes a grey wolf optimization method for solving the issue over a longer simulation period. Various cases were examined to evaluate the effectiveness of this suggested robust optimization algorithm. The outcomes show that the suggested model could not only reduce energy costs significantly but has also shown good performance for energy management purposes. [ABSTRACT FROM AUTHOR]

This paper introduces a hybrid algorithm that combines machine learning and modified teaching learning-based optimization (TLBO) for enhancing smart city communication and energy management. The primary objective is to optimize the modified systems, which face challenges due to their high population density. The proposed algorithm integrates the strengths of machine learning techniques, more specifically, the long short-term memory (LSTM) technique, with teaching learning-based optimization algorithms. To achieve optimization, the algorithm learns from historical data on energy consumption and communication patterns specific to the modeled system. By leveraging these insights, it can predict future energy consumption and communication patterns accurately. Additionally, the algorithm incorporates a modified teaching learning-based optimization approach inspired by the teaching and learning process in classrooms. It adjusts the system parameters based on feedback received from the system, thereby optimizing both energy consumption and communication systems. The effectiveness of the proposed algorithm is evaluated through a case study conducted on the test system, where historical data on energy consumption and communication patterns are analyzed. The results demonstrate that the algorithm efficiently optimizes the communication and energy management systems, leading to substantial energy savings and improved communication efficiency within the test system. In conclusion, this study presents a hybrid machine learning and modified teaching learning-based optimization algorithm that effectively addresses the communication and energy management challenges in the test system. Moreover, this algorithm holds the potential for application in various smart city domains beyond the test system. The findings of this research contribute to the advancement of smart city technologies and offer valuable insights into reducing energy consumption in densely populated urban areas. [ABSTRACT FROM AUTHOR]

This article proposes a novel stochastic framework based on point estimate method (PEM) and firefly algorithm (FA) for the optimal operation of plug-in electric vehicles (PVs) in the distribution systems. The stochastic problem will consider the uncertainties of active and reactive loads, the number of PVs in the fleets and the departure and arrival time at charging locations. According to the high complexity and severity of the problem, a new version of FA called θ-FA is used to search the solutions in the polar space instead of the traditional Cartesian space. The objective function is to minimize the total cost of the system considering the operation and security constraints. The feasibility and high performance of the propose problem are examined on a standard IEEE test system. [ABSTRACT FROM AUTHOR]

This paper suggests a new self-adaptive modification method using firefly algorithm (FA) to investigate the multi-objective probabilistic distribution feeder reconfiguration problem. In this regard, the idea of phase angle vector is employed to replace the traditional Cartesian framework in the FA and thus called θ-FA. Also, a new modification method based on an adaptive mechanism is suggested that will allow each firefly to choose the appropriate modification technique during the optimization suitably. As regards the objective functions, the main focus of this paper is to assess the effect of the reconfiguration on the reliability indices including active power losses, voltage deviation, and system average interruption frequency index. In order to handle the uncertainty effects, a sufficient framework based on 2 m + 1 point estimate method is proposed too. The satisfying performance of the proposed method is checked using IEEE 32-bus radial distribution system. Copyright © 2014 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

Plug-in Electric Vehicles (PEVs) will play significant role in the future smart grids. In this regard, the increasing appearance of PEVs can create new challenges in the optimal operation of these devices. In this way, this paper suggests a new method for optimal coordination of PEVs for reducing the total cost of the system during the day. The proposed method makes use of the idea of vehicle-to-grid (V2G) for shifting the energy demand in the grid. The problem is then formulated in an intelligent framework based on bat algorithm (BA) and Monte Carlo method to be solved optimally. Meanwhile, we suggest a new modification method for BA to improve its search ability for optimal coordination of PEVs. The proposed problem is examined on the IEEE test system with five PEV fleets. [ABSTRACT FROM AUTHOR]

This paper develops a new framework to solve the practical non-convex economic dispatch problem with regard to the constraints including ramp rate limits, valve loading effect, prohibited operating zone, spinning reserve and multi-fuel option. In the proposed framework, bat algorithm, as a new optimization algorithm, is employed to explore the problem search space globally. In addition, a newly introduced adaptive modification method is developed to improve the variety of the bat population when increasing the convergence speed simultaneously. This modification is constructed based on the roulette wheel mechanism in conjunction with the crossover and mutation operators from the genetic algorithm. At the end of paper, the superiority of the proposed framework is examined using the IEEE 10-unit and 40-unit test systems. [ABSTRACT FROM AUTHOR]

According to the significance of power load demand forecasting, this paper suggests a new hybrid method to reach more accurate model with fast response. The proposed model consists of two algorithms: Self Adaptive Modified Bat Algorithm (SAMBA) and Artificial Neural Network (ANN). In recent years, SAMBA has been used as a powerful tool in the optimization problems. On the other hand among the most popular methods, ANN has shown powerful performance in load prediction as the result of its ability to detect nonlinear mappings among different variables. In addition, the special ability of SAMBA in fast convergence, its low dependency to setting parameters and simple implementation make this algorithm more premiere than the other optimization algorithms. Therefore, in this paper for the first time we use SAMBA to regulate the weight matrix of ANN and optimize the degree of uncertainty which exist in load demand prediction. [ABSTRACT FROM AUTHOR]

This paper proposes a novel adaptive modification approach based on harmony search algorithm (HS) to solve the multi-objective environmental economic dispatch problem. The proposed algorithm makes use of adaptive formulations to update the adjusting parameters of HS including the pitch adjusting and bandwidth parameters and the harmony memory consideration rate during the optimization process. Meanwhile, a useful modification is proposed to improve the variety of the harmony population effectively. In order to handle both the cost and emission objective functions, the ideas of trapezoidal fuzzy membership function and weighting factor are employed. The satisfying performance of the proposed method is examined through the IEEE standard test system. [ABSTRACT FROM AUTHOR]

This paper deals with the optimal operation management of the distribution feeder reconfiguration (DFR) considering the uncertainty effects. In contrast to the conventional objective functions, this paper considers the System Average Interruption Frequency Index (SAIFI) as a reliability index. Meanwhile, the total active power losses and the voltage deviation objective functions are considered as the other targets too. In order to make the analysis more practical, the uncertainty associated with the active and reactive load forecast errors are modeled in a stochastic framework based on 2 m Point Estimate Method (PEM). In the proposed stochastic optimization framework, an external memory called repository is defined to store the non-dominated solutions which are found during the optimization process. Also, a fuzzy based clustering technique is defined to keep the size of the repository within the predefined limits. Since the proposed problem is a nonlinear, discrete complex optimization problem, this paper proposes an intelligent self adaptive modified optimization algorithm based on θ-firefly algorithm to solve the optimal multi-objective stochastic DFR problem suitably. The proposed self-adaptive modification method consists of three sub-modification techniques which let each firefly choose the sub-modification method that best suits its situation adaptively. The feasibility and superiority of the proposed method is tested on a standard IEEE test system. [ABSTRACT FROM AUTHOR]